schema · 13 fields
plant
Automate extraction for "plant". Extract structured, evidence-grounded data points directly from hundreds of papers with source page coordinates.
Schema Field Definitions (13)
| Field Name | Data Type | Description |
|---|---|---|
| plant_scientific_name | string | The full scientific name of the plant species. Example: 'Ginkgo biloba', 'Curcuma longa'. |
| plant_part | string | The part of the plant from which the compound was isolated. Must be one of: Leaf, Stem, Root, Flower, Seed, Bark, Fruit. |
| collection_location | string | The geographic location where the plant was collected, typically Country or Region. Example: 'Brazil', 'Yunnan Province'. |
| collection_date | date | The date the plant sample was collected, in YYYY-MM-DD format. |
| compound_name | string | The common or IUPAC name of the isolated compound. Example: 'Quercetin', 'Curcumin'. |
| compound_class | string | The chemical class of the compound. Example: 'Flavonoid', 'Terpenoid', 'Alkaloid'. |
| smiles_string | string | The Simplified Molecular-Input Line-Entry System (SMILES) string for the compound. Example: 'C1=CC(=C(C=C1C2=C(C(=O)C3=C(C=C(C=C3O2)O)O)O)O)O'. |
| inchi_key | string | The International Chemical Identifier Key (InChIKey) for the compound. Example: 'RFSUNJBCLKRZEA-UHFFFAOYSA-N'. |
| compound_yield | number | The yield of the isolated compound from the plant material, as a floating-point number. |
| compound_yield_unit | string | The unit for the compound yield. Must be one of: 'mg/g', '% w/w', 'mg/kg'. |
| extraction_method | string | The method used to extract the compound from the plant material. Example: 'Maceration', 'Soxhlet extraction', 'Supercritical fluid extraction'. |
| identification_technique | string | The primary analytical technique used to confirm the compound's structure. Example: 'NMR spectroscopy', 'Mass spectrometry', 'X-ray crystallography'. |
| doi | string | The Digital Object Identifier (DOI) of the source paper, as a string. Example: "10.1016/j.jep.2020.113429" |
Data Verification Status Taxonomy
To maintain rigorous scientific standards, Sci-database differentiates between automated signals and human audit:
Extracted
Value located and extracted from the full-text PDF by the Kateeb engine.
Model-Agreed
An independent second model produced a compatible value during automated second-pass review.
Human-Reviewed
A named researcher audited the value against the visual page coordinates.
Benchmark-Validated
Performance evaluated against a standardized, published evaluation protocol.
Replicated
An independent external research group reproduced the extraction and experimental result.